菜单
Use when building, testing, or verifying pea-core or the workspace. Run cargo build and cargo test for pea-core from repo root; fix compilation or test failures. Execute without asking for confirmation (autonomous mode).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when making architectural decisions, adding components, or understanding how PeaPod's pieces fit together. Provides context on the protocol design, component boundaries, and data flow to help agents make correct design choices.
Use when finishing a chunk of work or when the user asks to commit or to update Cursor context. Commit and push with a clear message; optionally add or update a rule, skill, or subagent in .cursor. Execute without prompting (autonomous mode).
Use when implementing features or fixes that correspond to .tasks checklists. Open the relevant .tasks file (e.g. 01-pea-core, 02-windows), implement unchecked items, and mark completed items with [x]. Run fully autonomously: no confirmation for build, test, commit, or push.
Use when working on Windows, Android, Linux, iOS, or macOS protocol implementations (pea-windows, pea-android, etc.). Follow the corresponding .tasks file (02–06); ensure wire format and discovery match pea-core and .tasks/07.
| name | peapod-build-test |
| description | Use when building, testing, or verifying pea-core or the workspace. Run cargo build and cargo test for pea-core from repo root; fix compilation or test failures. Execute without asking for confirmation (autonomous mode). |
Autonomous: Run build and test commands without asking for confirmation. Hooks allow shell execution automatically.
When building or verifying the project:
From the repo root, run:
cargo build -p pea-corecargo test -p pea-coreReport: State whether build and tests passed or failed. If they failed, fix the cause (compile errors, failing tests) and re-run until both pass.
Full workspace (optional): When working on pea-windows or pea-linux too, run cargo build and cargo test at the root to build and test all workspace members.
Scripts: Optional helper scripts are in this skill's scripts/ folder if present (e.g. build-and-test.ps1 for Windows). Prefer running the commands above directly when the agent can execute them.